Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sundance
    -0.08
    🏼
    -0.07
     Primary
    -0.07
    Firefox
    -0.07
     grootste
    -0.07
     firefox
    -0.07
    യും
    -0.07
     берен
    -0.07
    qy
    -0.07
    smöglichkeiten
    -0.07
    POSITIVE LOGITS
     Calder
    0.08
    -ra
    0.07
     justify
    0.07
    Exclusive
    0.07
     exclusive
    0.07
    Balanced
    0.07
     adjacent
    0.07
     valuables
    0.07
    �
    0.07
     connectivity
    0.07
    Act Density 0.002%

    No Known Activations